© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38325
    Prev
    Next
    INDEX
    Explanations

    light sensors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bikes
    -0.86
    Ladder
    -0.85
    Bicycle
    -0.84
     Giang
    -0.82
     OnEnable
    -0.76
    Personne
    -0.76
    Shipment
    -0.76
    ഞ
    -0.76
     बि
    -0.76
     conduire
    -0.75
    POSITIVE LOGITS
     sensors
    1.02
     wall
    0.97
     sensor
    0.96
     light
    0.96
     robot
    0.96
     cliff
    0.94
     right
    0.93
     bump
    0.91
     black
    0.90
     left
    0.89
    Activations Density 0.022%

    No Known Activations